东北大学学报(自然科学版) ›› 2011, Vol. 32 ›› Issue (2): 281-284.DOI: -

• 论著 • 上一篇    下一篇

实时高速棒材图像的识别与跟踪

王宏;郭璠;   

  1. 东北大学机械工程与自动化学院;
  • 收稿日期:2013-06-19 修回日期:2013-06-19 发布日期:2013-04-04
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(50435040)

Recognition and tracking method based on image of real-time and high-speed bar

Wang, Hong (1); Guo, Fan (1)   

  1. (1) School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China
  • Received:2013-06-19 Revised:2013-06-19 Published:2013-04-04
  • Contact: Guo, F.
  • About author:-
  • Supported by:
    -

摘要: 针对高速生产线上棒材计数困难的问题,使用线扫描相机采集运动棒材图像,利用Blob分析算法识别出棒材端面的质心坐标,并计算其面积大小;利用图像帧间数据联系开发出一种启发式跟踪方法跟踪棒材端面运动.在实验室环境下,开发出高速实时棒材识别与跟踪的硬件与软件系统.首先搭建了硬件平台,确定了硬件的系统参数,而后基于Visual Studio 2005平台进行了软件系统开发.实验结果证明,该系统对生产线上高速运动的不粘连棒材,计数准确率接近100%,且识别时间为毫秒级.

关键词: 图像处理, 线扫描相机, 实时系统, Blob算法, 跟踪关联

Abstract: It is difficult to count the bar sections moving at high speed on production line. To solve the problem, the line scanning camera is utilized to acquire the images of moving bars so as to recognize the centroid coordinates of the bars' ends and compute their area with a Blob algorithm, and a heuristic tracking algorithm is developed to track the moving bars' ends in relation to the interframe data. A hardware/software system is therefore developed for real-time recognition and tracking of the bars moving at high speed. First, hardware platform is set up and the system's parameters are determined. Second, the software system is developed on the basis of Visual Studio 2005. The experimental results showed that the system can well count bars moving at high speed on production line, with a counting accuracy near to 100% and a recognizing time in millisecond.

中图分类号: